Triple

T9936983
Position Surface form Disambiguated ID Type / Status
Subject Maleficent E193983 entity
Predicate director P255 FINISHED
Object Robert Stromberg
Robert Stromberg is an American production designer and visual effects artist who made his feature directorial debut with the fantasy film "Maleficent."
 E837887 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Robert Stromberg | Statement: [Maleficent, director, Robert Stromberg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Robert Stromberg
Context triple: [Maleficent, director, Robert Stromberg]
  • A. Gary Stromberg
    Gary Stromberg is a film producer best known for his work on the 1976 comedy film "Car Wash."
  • B. Fredric Steinkamp
    Fredric Steinkamp was an American film editor best known for his acclaimed work on major Hollywood productions, including the Oscar-winning epic "Out of Africa."
  • C. Ron Jensen
    Ron Jensen is an American politician who has served as the mayor of Grand Prairie, Texas.
  • D. Mark Stoermer
    Mark Stoermer is an American musician best known as the longtime bassist for the rock band The Killers.
  • E. Stephen Stucker
    Stephen Stucker was an American comic actor best known for his flamboyant, scene-stealing role as air traffic controller Johnny in the parody film "Airplane!".
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Robert Stromberg
Triple: [Maleficent, director, Robert Stromberg]
Generated description
Robert Stromberg is an American production designer and visual effects artist who made his feature directorial debut with the fantasy film "Maleficent."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Robert Stromberg
Target entity description: Robert Stromberg is an American production designer and visual effects artist who made his feature directorial debut with the fantasy film "Maleficent."
  • A. Gary Stromberg
    Gary Stromberg is a film producer best known for his work on the 1976 comedy film "Car Wash."
  • B. Fredric Steinkamp
    Fredric Steinkamp was an American film editor best known for his acclaimed work on major Hollywood productions, including the Oscar-winning epic "Out of Africa."
  • C. Ron Jensen
    Ron Jensen is an American politician who has served as the mayor of Grand Prairie, Texas.
  • D. Mark Stoermer
    Mark Stoermer is an American musician best known as the longtime bassist for the rock band The Killers.
  • E. Stephen Stucker
    Stephen Stucker was an American comic actor best known for his flamboyant, scene-stealing role as air traffic controller Johnny in the parody film "Airplane!".
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69ca82e409348190a393777356b80a2a completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb5e4e19881909879b394090d6629 completed April 2, 2026, 12:18 a.m.
NED1 Entity disambiguation (via context triple) batch_69d281d5f6188190a7e657b1bd9bc607 completed April 5, 2026, 3:37 p.m.
NEDg Description generation batch_69d2860be32081909eec066c19552ba5 completed April 5, 2026, 3:55 p.m.
NED2 Entity disambiguation (via description) batch_69d2865c11c881909b6791bd2bf503c4 completed April 5, 2026, 3:57 p.m.
Created at: March 30, 2026, 8:44 p.m.